How to Use the Evoliz MCP in AutoGen

Q: How do I register the Evoliz MCP Server tools in AutoGen?

Use autogen-extmcp to connect the server. You can then pass the tools directly to your AssistantAgent constructor, enabling agents to execute commands like listquotes.

Q: Can AutoGen agents resolve Evoliz invoice discrepancies on their own?

Yes. By assigning different roles, one agent can run getinvoice to identify errors, while another uses listarticles to retrieve correct pricing and propose a fix.

Let AutoGen agents debate and validate your Evoliz invoices and quotes for automated, compliant accounting via this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Evoliz MCP to AutoGen

Create your Vinkius account to connect Evoliz to AutoGen and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Evoliz with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent debate for French tax compliance

Let your agents double-check each other before finalizing financial records. One AutoGen agent can draft an invoice, while a secondary auditor agent calls `get_invoice` on the MCP Server to verify that the VAT rates and client details match French anti-fraud laws. If the auditor agent finds a discrepancy, it rejects the draft. The agents negotiate the corrections, fetch the correct catalog details using `get_article`, and only commit the changes once both agree the invoice is fully compliant.

Automated client verification via MCP Server tools

Prevent duplicate profiles and bad data. When a new customer signs up, your onboarding agent runs `list_clients` to search for existing records. If no match is found, it coordinates with the billing agent to execute `create_client` with the required professional details. The agents use `get_client` to double-check the newly created profile. This multi-step validation ensures that your customer database remains clean, organized, and compliant with French accounting standards.

Cooperative quote generation and review

Speed up your sales process with automated agent reviews. A sales agent drafts a proposal, while a pricing agent calls `list_articles` to verify current rates. Together, they construct a compliant quote through the MCP Server and execute `get_quote` to verify the generated document. This cooperative workflow removes the need for manual reviews. Your AutoGen agents handle the back-and-forth discussion, ensuring that every quote sent to a customer is accurate and backed by your live inventory.

Setup guide

Set up Evoliz MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Evoliz tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Evoliz_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Evoliz data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Evoliz_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Evoliz data")
    print(result.messages[-1].content)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Evoliz. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Evoliz now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Evoliz MCP in AutoGen

Use autogen-ext[mcp] to connect the server. You can then pass the tools directly to your AssistantAgent constructor, enabling agents to execute commands like `list_quotes`.

Yes. By assigning different roles, one agent can run `get_invoice` to identify errors, while another uses `list_articles` to retrieve correct pricing and propose a fix.

Your agents communicate in a group chat. An onboarding agent gathers the details, a compliance agent verifies them, and a writer agent executes `create_client` to register the new customer.

It does. You can set up a round-robin conversation where agents analyze a request, call `get_quote` to inspect the draft, and vote on whether to approve the document.

Yes. Your client profiles, quote drafts, and financial ledgers are processed securely. The Vinkius infrastructure runs the server in an isolated sandbox, keeping your API transactions private and secure.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript